arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2112.12754cs.AI
收藏

走向新的常识科学

Toward a New Science of Common Sense

Jacobs Technion-Cornell Institute(雅各布斯以色列理工学院-康奈尔大学研究院);Cornell University(康奈尔大学);University of Toronto(多伦多大学)

Ronald J. Brachman, Hector J. Levesque

摘要:

常识一直是人工智能的兴趣所在,但很少占据中心舞台。尽管John McCarthy最早的论文之一和专门研究人员多年的工作中提到了它,但可以说没有出现过具有大量一般常识的人工智能系统。为什么会这样?少了什么?人工智能系统缺乏常识的例子比比皆是,它们指出人工智能经常关注专业知识是原因。即使在现代深度学习的背景下,那些试图打破由此产生的脆性障碍的人也倾向于将精力投入到大量的小常识知识上。虽然很重要,但世界上所有的常识知识片段并不能组成一个系统,以类似人类的方式展示常识。我们主张从比过去更广泛的角度来审视常识。常识应该在一个完整的认知系统中考虑,包括历史、目标、欲望和驱动力,而不仅仅是孤立的限制性例子。需要一个新的面貌:常识值得进行专门的科学探索。

英文摘要:

Common sense has always been of interest in Artificial Intelligence, but has rarely taken center stage. Despite its mention in one of John McCarthy's earliest papers and years of work by dedicated researchers, arguably no AI system with a serious amount of general common sense has ever emerged. Why is that? What's missing? Examples of AI systems' failures of common sense abound, and they point to AI's frequent focus on expertise as the cause. Those attempting to break the resulting brittleness barrier, even in the context of modern deep learning, have tended to invest their energy in large numbers of small bits of commonsense knowledge. While important, all the commonsense knowledge fragments in the world don't add up to a system that actually demonstrates common sense in a human-like way. We advocate examining common sense from a broader perspective than in the past. Common sense should be considered in the context of a full cognitive system with history, goals, desires, and drives, not just in isolated circumscribed examples. A fresh look is needed: common sense is worthy of its own dedicated scientific exploration.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑